Advanced search
1 file | 366.53 KB

A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI

(2012) PLOS ONE. 7(4).
Author
Organization
Abstract
This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.
Keywords
P300 WAVE, ALGORITHM, COMMUNICATION, COMPETITION 2003, MENTAL PROSTHESIS, BRAIN-COMPUTER-INTERFACE

Downloads

  • plos template.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 366.53 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Kindermans, Pieter-Jan, David Verstraeten, and Benjamin Schrauwen. 2012. “A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300 Based BCI.” Plos One 7 (4).
APA
Kindermans, P.-J., Verstraeten, D., & Schrauwen, B. (2012). A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI. PLOS ONE, 7(4).
Vancouver
1.
Kindermans P-J, Verstraeten D, Schrauwen B. A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI. PLOS ONE. 2012;7(4).
MLA
Kindermans, Pieter-Jan, David Verstraeten, and Benjamin Schrauwen. “A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300 Based BCI.” PLOS ONE 7.4 (2012): n. pag. Print.
@article{2046642,
  abstract     = {This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.},
  articleno    = {e33758},
  author       = {Kindermans, Pieter-Jan and Verstraeten, David and Schrauwen, Benjamin},
  issn         = {1932-6203},
  journal      = {PLOS ONE},
  keyword      = {P300 WAVE,ALGORITHM,COMMUNICATION,COMPETITION 2003,MENTAL PROSTHESIS,BRAIN-COMPUTER-INTERFACE},
  language     = {eng},
  number       = {4},
  pages        = {21},
  title        = {A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI},
  url          = {http://dx.doi.org/10.1371/journal.pone.0033758},
  volume       = {7},
  year         = {2012},
}

Altmetric
View in Altmetric
Web of Science
Times cited: